TheoremSmith
Making models better at formal verification will help push the boundaries of math research and significantly reduce the number of bugs in our code.
TheoremSmith launched on 10 November 2026. It ranked #118 on Daily Launch on 11 November 2026 with a Launch Score of 10, from 10 points on Show HN. It was new in the ranking that day.
What is TheoremSmith?
Making models better at formal verification will help push the boundaries of math research and significantly reduce the number of bugs in our code. Recently, training models on RL environments (tasks paired with verifiers that reward correct solutions) has driven big gains in model performance, and proofs are unusually easy to verify. Here we introduce TheoremSmith, a pipeline for generating synthetic formal verification environments. It reliably creates multi-hour, frontier-difficulty tasks and can scale throughput effectively.
From its Hacker News post
TheoremSmith is a launch on Show HN.
In its own words
Mass-Producing Hard Proof Problems to Train LLMs
From its Show HN post
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 10 of 100 on 11 November.